I^3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors

03/25/2021
by   Chaoqi Chen, et al.
14

Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features to design fine-grained feature alignment modules with respect to the foreground objects. However, for one-stage detectors, it is hard or even impossible to obtain explicit instance-level features in the detection pipelines. Motivated by this, we propose an Implicit Instance-Invariant Network (I^3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers. Specifically, we facilitate the adaptation from three aspects: (1) Dynamic and Class-Balanced Reweighting (DCBR) strategy, which considers the coexistence of intra-domain and intra-class variations to assign larger weights to those sample-scarce categories and easy-to-adapt samples; (2) Category-aware Object Pattern Matching (COPM) module, which boosts the cross-domain foreground objects matching guided by the categorical information and suppresses the uninformative background features; (3) Regularized Joint Category Alignment (RJCA) module, which jointly enforces the category alignment at different domain-specific layers with a consistency regularization. Experiments reveal that I^3Net exceeds the state-of-the-art performance on benchmark datasets.

READ FULL TEXT
research
09/15/2023

Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors

Cross-domain pedestrian detection aims to generalize pedestrian detector...
research
06/26/2021

Domain Adaptive YOLO for One-Stage Cross-Domain Detection

Domain shift is a major challenge for object detectors to generalize wel...
research
03/23/2020

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

Recent years have witnessed great progress in deep learning based object...
research
04/05/2020

Deeply Aligned Adaptation for Cross-domain Object Detection

Cross-domain object detection has recently attracted more and more atten...
research
06/06/2022

Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection

Domain Adaptive Object Detection (DAOD) focuses on improving the general...
research
08/30/2021

Densely Semantic Enhancement for Domain Adaptive Region-free Detectors

Unsupervised domain adaptive object detection aims to adapt a well-train...
research
03/13/2020

Harmonizing Transferability and Discriminability for Adapting Object Detectors

Recent advances in adaptive object detection have achieved compelling re...

Please sign up or login with your details

Forgot password? Click here to reset